# Import libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd from pandas import DataFrame, Series import seaborn as sns # from sklearn.cluster import KMeans from sklearn.datasets import make_blobs

# # Create a data set in 2 dimensions using make_blobs # # The function make_blobs stores the data in x and the cluster each point belongs to in y # (x,y)= make_blobs ( n_samples =200, n_features=2,centers=5,cluster_std=0.5, shuffle=True,random_state=0 ) plt.scatter( x[:,0],x[:,1], c='white', edgecolor='black',marker='o', s=50) plt.show()

# Calculate centroids of blobs; remember that the array y contains cluster number n = len(y) n_blobs=5 n_points_blob = 40. blob_mean = np.zeros( ( n_blobs,2) ) # # Loop to sum up x and y coordinates of each point in blob for i in range (0,n): blob=y[i] # given blob index (0,1,2,3,4) blob_mean [blob,0] = blob_mean [blob,0] + x[i,0] blob_mean [blob,1] = blob_mean [blob,1] + x[i,1] # Loop to divide by number of points in blob and print out for k in range (0,n_blobs) : blob_mean [k,:] = blob_mean [k,:] / n_points_blob print (f"Blob {k+1} has centroid: ( { blob_mean [k,0] }, { blob_mean [k,1] } ) " )

# Create KMeans model and fit data in array x which is in the correct shape: 200 by 2 kmeans = KMeans(n_clusters=3,init='random',random_state=0) kmeans.fit(x)

# Plot clusters using colors and compare visually with blob plot above plt.scatter(x[:,0],x[:,1],c=kmeans.labels_,cmap='viridis') plt.scatter(kmeans.cluster_centers_[:,0],kmeans.cluster_centers_[:,1],marker='x',c='black',label='centroids') plt.legend(scatterpoints=1) plt.show() plt.scatter(x[:,0],x[:,1],c='white',edgecolors='black',marker='o',s=50) plt.show()

# Print out final clusters centroids and print out actual centroids to compare # print (" KMeans Centroids ", " Original Centroids ") print(f" {kmeans.cluster_centers_} {blob_mean}" ) # Note that Kmeans cluster 3 corresponds to our cluster 5 and vice versa

# 1 iteration centroids = np.array( [ [-3,-2], [-2,12], [3,8], [12,0], [2,12] ]) print () print ("******************************************") print ("Results for 1st iteration of KMeans") kmeans_model = KMeans(n_clusters=5,init=centroids,max_iter=1) kmeans_model.fit(x) print (f'The Centroids are {kmeans_model.cluster_centers_}') plt.scatter(x[:,0],x[:,1],c=kmeans_model.labels_,cmap='viridis') plt.title('1 iteration') plt.show()

# 2 iterations centroids = np.array( [ [-3,-2], [-2,12], [3,8], [12,0], [2,12] ]) print () print ("******************************************") print ("Results for 2nd iteration of KMeans") kmeans_model_2 = KMeans(n_clusters=5,init=centroids,max_iter=2) kmeans_model_2.fit(x) print (f'The Centroids are {kmeans_model_2.cluster_centers_}') plt.scatter(x[:,0],x[:,1],c=kmeans_model_2.labels_,cmap='viridis') plt.title('2 iterations') plt.show()

# Import libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd from pandas import DataFrame, Series import seaborn as sns # Import models from sklearn.cluster import KMeans

# Create dataframe from file insurance.csv df = pd.read_csv('insurance.csv')

#Create a new dataframe which only has the two features (age and bmi)and the charges # new_df = df[['age','bmi','charges']].copy()

# Determine how many data instances there are new_df.info() # so 1338 data instances

# Find the maximum & minimum value of the charges print(f'The minimum of charges is {min(new_df.charges)}') print(f'The maximum of charges is {max(new_df.charges)}')

# Print out the data instance where the max occurs print(max(new_df.charges))

# Print out all data instances where charges are >60,000 charges = new_df.charges.values bmi = new_df.bmi.values for charge in charges: if charge > 60000: print(charge)

# Print out all data instances where bmi > 35 and charges > 50,000 print (new_df[(new_df['bmi']>35) & (new_df['charges']>50000)])

# Delete all data instances where the charges are more than $60,000 df_without_charge_outliers = new_df[new_df.charges < 60000] new_charges_column = df_without_charge_outliers['charges'] # Print out all data instances where charges are >60000 to check for i in new_charges_column: if i > 60000: print(i)

# Scale costs between $0 and $100; round costs to 2 decimal places (for cents) # print out the first few entries to check charge_min=min(new_charges_column) charge_max=max(new_charges_column) scaled_cost = 100 * (new_charges_column-charge_min)/(charge_max-charge_min) rounded_cost=np.round(scaled_cost,2) print(rounded_cost)

# Add column to dataframe with scaled charges and remove column with full charges df_without_charge_outliers['scaled and rounded costs'] = rounded_cost df.drop(columns = ['charges'])

# Create 2D array and use KMeans with 4 clusters x = np.array(rounded_cost) n=len(x) x=np.reshape(x,(n,1)) km = KMeans(n_clusters=4) km.fit(x)

# Print out the labels print(km.labels_) # # add column to dataframe giving cluster labels df_without_charge_outliers['clusters'] = km.labels_

# Set white background grid for Seaborn plots sns.set_style ( "whitegrid")

# Create scatterplot of charges vs bmi with cluster indiciated by hue using Seaborn's relplot sns.relplot(x='charges',y='bmi',data=df_without_charge_outliers,hue='clusters')

# Create scatterplot of charges vs age with cluster indiciated by hue using Seaborn's relplot sns.relplot(x='charges',y='age',data=df_without_charge_outliers,hue='clusters')